{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZNQ5SZBE2QNG4BJYTILXRWYFSR","short_pith_number":"pith:ZNQ5SZBE","schema_version":"1.0","canonical_sha256":"cb61d96424d41a6e05389a1778db059476c13b1d2311f4a31cdb72d3aaab6326","source":{"kind":"arxiv","id":"2607.02290","version":1},"attestation_state":"computed","paper":{"title":"DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junchi Yan, Leyao Gu, Mingxin Liu, Mohan Zhang, Ning Liao, Shaofeng Zhang, Xiangyu Zhao, Xuanhe Zhou, Xue Yang, Yiguo He, Zhaokai Wang, Zhihang Zhong, Ziqian Fan, Zirun Zhu","submitted_at":"2026-07-02T15:07:47Z","abstract_excerpt":"Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a knowledge-intensive diagram whose correctness depends on disciplinary concepts, symbolic structure, and precise spatial relations. We introduce DisciplineGen-1M, a million-scale multidisciplinary dataset that supports text-to-image generation and image editing. It contains 1.2M samples spanning mathematics, physics, chemistry, biology, geography, computer science, economics, history, music, and sports. To construct the dataset, we design a scalable fra"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.02290","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T15:07:47Z","cross_cats_sorted":[],"title_canon_sha256":"38b041d45e8885bf8de084000ecbc5a21c189786cf0218aaa662e806469abb7c","abstract_canon_sha256":"01ad9d960717c3cfddf77ffd65d23ead923fe95d05b29bc20dca7cfe6d69ca46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:47.634884Z","signature_b64":"HziZOIRGfzyElhdyL1BCLBUgFEKnDUo/Mo4+p1xqxizjZ04Uopg0tdzzUkYqg7iBlpw3fx9M6szRkIqEbsixBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb61d96424d41a6e05389a1778db059476c13b1d2311f4a31cdb72d3aaab6326","last_reissued_at":"2026-07-03T01:17:47.634488Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:47.634488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junchi Yan, Leyao Gu, Mingxin Liu, Mohan Zhang, Ning Liao, Shaofeng Zhang, Xiangyu Zhao, Xuanhe Zhou, Xue Yang, Yiguo He, Zhaokai Wang, Zhihang Zhong, Ziqian Fan, Zirun Zhu","submitted_at":"2026-07-02T15:07:47Z","abstract_excerpt":"Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a knowledge-intensive diagram whose correctness depends on disciplinary concepts, symbolic structure, and precise spatial relations. We introduce DisciplineGen-1M, a million-scale multidisciplinary dataset that supports text-to-image generation and image editing. It contains 1.2M samples spanning mathematics, physics, chemistry, biology, geography, computer science, economics, history, music, and sports. To construct the dataset, we design a scalable fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02290","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.02290/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.02290","created_at":"2026-07-03T01:17:47.634555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02290v1","created_at":"2026-07-03T01:17:47.634555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02290","created_at":"2026-07-03T01:17:47.634555+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNQ5SZBE2QNG","created_at":"2026-07-03T01:17:47.634555+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNQ5SZBE2QNG4BJY","created_at":"2026-07-03T01:17:47.634555+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNQ5SZBE","created_at":"2026-07-03T01:17:47.634555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR","json":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR.json","graph_json":"https://pith.science/api/pith-number/ZNQ5SZBE2QNG4BJYTILXRWYFSR/graph.json","events_json":"https://pith.science/api/pith-number/ZNQ5SZBE2QNG4BJYTILXRWYFSR/events.json","paper":"https://pith.science/paper/ZNQ5SZBE"},"agent_actions":{"view_html":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR","download_json":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR.json","view_paper":"https://pith.science/paper/ZNQ5SZBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02290&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNQ5SZBE2QNG4BJYTILXRWYFSR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNQ5SZBE2QNG4BJYTILXRWYFSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR/action/storage_attestation","attest_author":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR/action/author_attestation","sign_citation":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR/action/citation_signature","submit_replication":"https://pith.science/pith/ZNQ5SZBE2QNG4BJYTILXRWYFSR/action/replication_record"}},"created_at":"2026-07-03T01:17:47.634555+00:00","updated_at":"2026-07-03T01:17:47.634555+00:00"}